Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jpm1118/threadwork/subagent-driven-developmentnpx skills add JPM1118/Threadwork --skill subagent-driven-developmentgit clone --depth 1 https://github.com/JPM1118/ThreadworkWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02087 |
| Opus 5 | $0.00000 | $0.01043 |
| Sonnet 5 | $0.00000 | $0.00417 |
| Haiku 4.5 | $0.00000 | $0.00209 |
Grade A, and why
subagent-driven-development scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Development Skill
Execute implementation plans using independent subagents per task with automated code review between tasks.
Core Principle
FRESH SUBAGENT PER TASK
Each task gets a new subagent. This prevents context pollution and ensures focused execution.
When to Use This Skill
Use subagent-driven development when:
- Staying in the current session for continuous progress
- Tasks are mostly independent
- You want automated quality gates between tasks
- Orchestrating work rather than implementing directly
When NOT to Use This Skill
Don't use when:
- Tasks require heavy context from previous tasks
- You're the one implementing (use beads-tdd-execution directly)
- Tasks are tiny (overhead not worth it)
- You need real-time human feedback between tasks
Prerequisites
- Beads-backed plan exists with ready tasks
- You're acting as orchestrator
- Tasks are well-defined with clear acceptance criteria
The Subagent Development Flow
┌─────────────────────────────────────────────────────────────┐
│ Subagent-Driven Development Flow │
├─────────────────────────────────────────────────────────────┤
│ │
│ For each task: │
│ │
│ 1. GET READY TASK │
│ ↓ bd ready → task-id │
│ │
│ 2. SET IN PROGRESS │
│ ↓ bd edit --status in_progress │
│ │
│ 3. DISPATCH SUBAGENT │
│ ↓ Task tool → implementation subagent │
│ │
│ 4. RECEIVE REPORT │
│ ↓ Subagent returns completion report │
│ │
│ 5. RUN CODE REVIEW │
│ ↓ Dispatch code-reviewer subagent │
│ │
│ 6. HANDLE REVIEW RESULTS │
│ ↓ Fix issues if needed (dispatch fix subagent) │
│ │
│ 7. CLOSE TASK │
│ ↓ bd close with evidence │
│ │
│ Repeat for next task │
│ │
└─────────────────────────────────────────────────────────────┘
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 348 lines · 0 tokens per session scan A a1ddc00f3837
subagent-driven-development is a skill published in the GitHub repository JPM1118/Threadwork (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,087 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…